Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4459 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.6927. Min Act: -0.1700
Data Index: 4918966 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.6614. Min Act: -0.1700
Data Index: 4142352 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.5989. Min Act: -0.1700
Data Index: 3135512 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.5677. Min Act: -0.1700
Data Index: 5991665 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.5364. Min Act: -0.1700
Data Index: 5123924 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.5052. Min Act: -0.1700
Data Index: 1345885 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.4114. Min Act: -0.1700
Data Index: 8678625 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.3802. Min Act: -0.1700
Data Index: 3633105 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.3489. Min Act: -0.1700
Data Index: 3919613 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.2864. Min Act: -0.1700
Data Index: 5473571 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.2552. Min Act: -0.1700
Data Index: 6539318 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.2552. Min Act: -0.1700
Data Index: 8472321 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.2552. Min Act: -0.1700
Data Index: 6698307 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.2239. Min Act: -0.1700
Data Index: 6895405 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.2239. Min Act: -0.1700
Data Index: 477416 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.2239. Min Act: -0.1700
Data Index: 1357176 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.2239. Min Act: -0.1700
Data Index: 4100092 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.1927. Min Act: -0.1700
Data Index: 1357465 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.1927. Min Act: -0.1700
Data Index: 4454999 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6927. Min Range: -6.6927
Max Act: 6.1614. Min Act: -0.1700
Data Index: 7420979 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19